63stack

They will roll out the "trusted agent platform sandbox" (I'm sure they will spend some time on a catchy name, like MythosGuard), and for only $19/month it will protect you from mistakes like throwing away your prod infra because the agent convinced itself that that is the right thing to do.

Of course MythosGuard won't be a complete solution either, but it will be just enough to steer the discourse into the "it's your own fault for running without MythosGuard really" area.

Which model are you using it with? I imagine it's bring your own model?

Fingers crossed on RAM/HDD/GPU prices coming back

Unfortunately you won't be able to submit any expenses then, because the company uses this other company who only offers an app for accounting.

Yes you will download the app because we will not offer a web version.

I agree with parent, "having a contract" gives you nothing tangible. Big tech providers get hacked quite commonly nowadays, some with glaringly embarrassing vulnerabilities like "the admin password was admin". All your data leaks, and the most you get from them going "sorry".

Having the ability to sue, and having the resources to sue is also not the same.

The amount of times I had to deal with support cases (as the reporter, not the handler) where I felt like the support person was actually incentivized to solve my problem vs just following the script is astonishingly low. Even with paid support. Paid support just means you get to follow their script faster.

Debian requires unattended-upgrades to be installed (it's not installed by default), Mint and Fedora has the option of enabling automatic updates (disabled by default), Arch has no mechanism for automatic updates.

Which ones are these "most distros"?

Linux as in the kernel? Who is "they"? Torvalds?

It's not broken, it's the process ???

What would you consider broken?

Github has posted that they will now train on everyone's data (even private) unless you opt out (until they change their mind on that). Anthropic has been training on your data on certain tiers already. Meta bittorrented books to train their models.

Surely if your license says "LLM output trained on this code is legally tainted", it is going to dissuade them.

Is this the first time you are reading HN? Every day there are posts from people describing how AI crawlers are hammering their sites, with no end. Filtering user agents doesn't work because they spoof it, filtering IPs doesn't work because they use residential IPs. Robots.txt is a summer child's dream.

The article starts off really weak:

>Claude Code users typically treat the .claude folder like a black box. They know it exists. They’ve seen it appear in their project root. But they’ve never opened it, let alone understood what every file inside it does.

I know we are living in a post-engineering world now, but you can't tell me that people don't look at PRs anymore, or their own diffs, at least until/if they decide to .gitignore .claude.

Not that I'm entirely onboard with it, but often you don't have a channel to communicate with "the people who can change the machine", only the cogs in the machine.

If the schedules align they will pick up, if not they will see the missed call and call back when they have time.

Both are measuring the amount of data transferred, one with hot cache, other is without. The number is not inflated.

Is this the Bram Cohen who made bittorrent? There is surprisingly little information on this page.

Assuming good faith and giving the benefit of the doubt to google is just naivety.

They have shown time and time again that they will take as much control from you as they can.

AKA, just send your actual message directly and leave out the llm.

I agree. If I see "unfortunately we receive hundreds of applications from people who don't read the job description, please include the word banana in your application" I will be sympathetic. If I "see interview with our ai bot first" I will nope out.

I was wondering the same thing. It already takes a very high level of motivation and self discipline to go 3 times a week, going every day requires superhuman levels to so consistently.

This doesn't take into account that your body requires rest, and I don't know how op thinks you can combine this with an active sport like skiing, or something creative like music. You will be drained already from the gym.

I don't think this is an old man rant, I think you made a reasonable argument. Rust is certainly at risk of becoming just as complex as c++.

I would love to introduce more rust at work, but I dread that someone is going to ask about for<'a>, use<'a>, differences between impl X vs Box<dyn X>, or Pin/Unpin, and I don't have proper answers either.

I removed this line because people will get hung up on it and not see the forest from the tree.

I agree completely, the "democratizing programming" is being overplayed by AI vendors like they are doing community service, and HN commenters use it like a trump card in an argument.

Everyone already had the option to write any code, fork any open source project, publish any of their code, run any of their code but suddenly AI appears and THAT is what makes it democratic? What was undemocratic about it? Is this democracy where idiots are running ai agents that publish smear campaigns, or harass maintainers for not accepting their slop is the democratic future you wish for?

How many (job) positions do you see today that want a backend developer? Frontend developer? Not much because now everyone is expected to be at least full stack, if not also devops as well. The exact same thing is playing out right now with AI, people are expected to produce 5x the amount of code before, if you don't, someone else will take your job that is willing to do it.

Already bloated programs will bloat further, they will require even more resources to run, you will have to pay even more for hardware, they will be slower, less responsive, you will have to pay yet another monthly fee to big tech for their AIs, and people will happily do it and pat themselves that we democratized programming, while running towards the future where nobody will be able to own hardware capable of general computing.

I would love this to be expanded to public transport in general. Fine them for the same amount as traveling without a ticket. It would clear up so fast.

People are rushing to be the first one to coin something and hit it big. Imagine the amount of $$$ you could get for being an "expert ai consultant" in this space.

There was already another attempt at agentic patterns earlier:

https://agentic-patterns.com/

Absolute hot air garbage.

I thought you can't even get that if you are in an area that is often flooded.

I doubt anyone would blame google for not forcibly enabling 2fa.

I'm in central europe, atm 70 TV channels is $15/month.

I'm in central europe, atm 70 TV channels is $15/month.

I'm pretty sure "how do we disallow running our agents in screen sessions" is on a jira board at some places